Publications

Tensor Cookbook: Mastering Tensors through Diagrams

Beheshteh T. Rakhshan

High-dimensional data arise naturally in many areas of science and engineering, including machine learning, signal processing, computational… (voir plus) physics, and statistics. Such data are often represented as tensors, multi-dimensional generalizations of matrices. While tensors provide a natural representation for multi-modal structure, their direct manipulation quickly becomes challenging as the order grows: the number of parameters increases exponentially, and algebraic expressions involving many indices become difficult to interpret and implement. Tensor networks (TNs) provide an effective framework for addressing these challenges. Originally introduced by Penrose and developed extensively in quantum physics, the graphical language of tensor networks encodes contractions as edges in a graph, reducing notational overhead and revealing structural properties obscured by index notation. Despite the central role of high-dimensional tensors in modern machine learning and numerical analysis, tensor network diagrams remain underutilized outside quantum computing, partly due to the lack of a self-contained mathematical reference accessible to a broad technical audience. This manuscript provides a self-contained guide to tensor networks and their use in tensor algebra. We present the main operations on tensors, contractions, products, and reshaping through, graphical notation, and show how classical tensor decompositions and related computations are naturally expressed in this framework. We also illustrate how tensor networks simplify the derivation of gradients and the manipulation of high-dimensional probability distributions. Throughout, we show that the diagrammatic approach yields genuinely shorter and more transparent proofs of classical identities, rank bounds, and gradient formulas that would otherwise require laborious index manipulation.

2026-05-14

arXiv (prépublication)

doi.org

arxiv.org

Vision-Based Semantic SLAM for Autonomous Navigation in Mill Yard

Junrui Huang

Inna Sharf

Elie Ayoub

Nicolas Lemieux

Heshan Fernando

Log-loading machines are essential in mill-yard operations for unloading logs from incoming transport trucks onto mill infeed deck, as well … (voir plus)as managing log inventory in stockpiles. This paper focuses on the log-loading operation in the vicinity of the infeed deck, with the goal of enabling higher levels of autonomy in this task. Near the infeed deck, the machine must localize reliably relative to the infeed deck and adjacent buffer piles, while also detecting and localizing arriving trucks and trailers; this is a highly dynamic outdoor environment. We present a vision-based semantic SLAM system that uses a stereo camera mounted on the log-loading machine as the sole perception sensor. The proposed pipeline is based on stereo ORB-SLAM2 for real-time pose estimation and mapping. It integrates a parallel semantic thread that converts stereo depth into pseudo-LiDAR point clouds and predicts oriented 3D bounding boxes for key objects, including the infeed deck, log piles, and log trucks. The estimated 3D bounding boxes are used to remove features on potentially dynamic objects during SLAM tracking for improving robustness, and to construct a persistent object-level semantic map by transforming 3D bounding boxes into the global SLAM frame. We evaluated the system in a virtual NVIDIA Isaac Sim infeed-deck environment using synthetic stereo image sequences. The evaluation reports camera trajectory accuracy, semantic object localization accuracy, and runtime performance, and includes ablations to isolate the impact of dynamic-feature removal and object-level semantic mapping. The results indicate that incorporating object-level 3D detections improves the robustness and accuracy of stereo SLAM in dynamic infeed-deck scenes while producing a globally consistent semantic map in practical runtime.

2026-05-13

Conference on Robots and Vision (publié)

doi.org

World models, artificial general intelligence and the hard problems of life–mind continuity: toward a unified understanding of natural and artificial intelligence

Adam Safron

Michael Levin

Victoria Klimaj

Zahra Sheikhbahaee

Dalton Sakthivadivel

Adeel Razi

David Ha

Nick Hay

Kevin Schmidt

Irina Rish

David Krakauer

Melanie Mitchell

Samuel J. Gershman

Joshua B. Tenenbaum

Abstract This special issue examines how natural and artificial intelligences (AIs) model the world, and what this modelling reveals about c… (voir plus)ognition and relationships between life and mind. Rather than adopting a single definition, the collection considers how world models function and emerge in biological and artificial systems, exploring a diverse range of world modelling including causal, self-referential, individual goal-directed, collective and narrative forms. A recurring theme is the extent to which current AI systems trained on vast quantities of data learn the context-sensitive, temporally embedded, value-laden dimensions of world modelling that characterize diverse biological intelligences, or whether their impressive capabilities arise primarily from statistical surface regularities. The contributions also raise broader issues concerning embodiment, complexity, learning architectures and the social and scientific contexts in which world models operate. With this collection, we hope to clarify the conceptual landscape, identify key points of similarity and divergence between natural and artificial minds, and outline questions that may guide future research on the forms of world modelling that support grounded understanding, robust agency and potentially human-like general intelligence. This article is part of the theme issue ‘World models in natural and artificial intelligence’.

2026-05-13

Philosophical Transactions of Royal Society A: Mathematical, Physical and Engineering Sciences (publié)

doi.org

Bidirectional modulation of pain by neurofeedback: Preliminary findings with fMRI at 7T

Konstantin A. Demin

Jun Seo Hwang

Wonyi Che

Dongho Kim

Wani Woo

Hakwan Lau

Vincent Taschereau‐Dumouchel

Abstract Previous brain decoding studies indicate that an individual’s pain experience can be robustly predicted from distributed patterns… (voir plus) of brain activity. Two brain decoders have notably been associated respectively with the nociceptive and cognitive aspects of pain experience, the Neurologic Pain Signature (NPS) and the Stimulus-Intensity Independent Pain Signature (SIIPS). Yet, we still do not know if these brain patterns are also causally related to pain experience. To evaluate this possibility, we used high-field (7-Tesla) fMRI to test whether humans can alter their pain experience by bidirectionally modulating their pain-related brain activity in decoded neurofeedback paradigm. In a double-blind design, participants were trained to up- and down-regulate the NPS or the SIIPS. Our results indicate that participants can achieve bidirectional control of both signatures. NPS expression reliably increased during pain stimulation and covaried with both stimulus intensity and subjective ratings. In contrast, SIIPS expression did not show consistent stimulus-locked effects in the primary analyses. Importantly, reduction in pain rating was specific for SIIPS-training, whereas NPS has failed to show any consistent behavioral effect. Based on these preliminary findings, we hereby preregister a follow-up study, with specified rationale, hypotheses, experimental design, and analysis protocols.

2026-05-12

bioRxiv (prépublication)

doi.org

CA2: Code-Aware Agent for Automated Game Testing

Valliappan Chidambaram Adaikkappan

Vincent Martineau

Joshua Romoff

David Meger

Automated game testing is important for verifying game functionality, but it remains a costly and time-consuming process. Manual testing oft… (voir plus)en misses edge cases, and current automated methods struggle to provide full code coverage. Prior work has explored reinforcement learning (RL) for game testing, but without leveraging internal code signals such as the call stack. We present Code Aware Agent (CA2), which uses call stack information to learn effective testing strategies. The agent receives the current function call trace along with the game state and learns to reach specific target functions. We instrument two types of environments, 1) State-based and 2) Image-based, with support for efficient call stack extraction. Through experimental evaluation, we find that CA2 achieves consistent improvement over the non-code aware baselines, which does not leverage call stack information. Our results show that incorporating code signals like the call stack enables more effective and targeted game testing.

2026-05-12

arXiv (prépublication)

doi.org

arxiv.org

Path-independent Flow Matching for Multi-parameter Generative Dynamics

Sina Sanjari

Yanlei Zhang

Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formu… (voir plus)lation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is crucial because it ensures that transformations depend only on the initial and target distributions, not on the specific path. In this work, we introduce Path-independent Flow Matching (PiFM), a method for learning vector fields whose induced flows yield path-independent transport between distributions. We show that PiFM generalizes Flow Matching to higher-dimensional parameter domains while enforcing structural conditions that ensure consistency of composed transformations. In addition, we show that, under suitable assumptions, PiFM approximates the Wasserstein barycenter, linking the framework to a notion of distributional interpolation. To enable practical training, we propose a tractable, simulation-free objective that regresses onto multi-parameter conditional probability paths. We showcase empirically that PiFM outperforms other approaches on both synthetic and real world data in interpolating path-independent trajectories and generating desired out of distribution samples.

2026-05-12

arXiv (prépublication)

doi.org

openreview.net

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation

Vikash Singh

Debargha Ganguly

Weicong Chen

Sabyasachi Sahoo

Sreehari Sankar

Biyao Zhang

Mohsen Hariri

Shouren Wang

Osama Zafar

Christian Gagné

Vipin Chaudhary

Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a froze… (voir plus)n source checkpoint. This anchor is useful only when the source remains reliable. On CCC-Hard, however, a ResNet-50 source falls to approximately

2026-05-12

arXiv (prépublication)

doi.org

arxiv.org

Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data

Paul Hoareau

Kuan Yi Wang

Brandon Bujak

Roy Sun

Govind Nair

Irene Cortese

Charidimos Tsagkas

Daniel Reich

Julien Cohen-Adad

INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, … (voir plus)forcing reliance on sparse 2D slices. Weakly supervised Sparse-to-Dense frameworks bridge this gap, but guidelines remain ambiguous regarding human-centric visual enhancements and transferring optimization strategies across dimensions. We analyze divergent regularization needs for multi-class segmentation of high-resolution ex vivo spinal cord MRI. METHODS | We used 9.4T MRI of multiple sclerosis spinal cords (>104,000 slices) with sparse annotations (428 slices). A 2D Teacher trained on sparse slices generated dense pseudo-labels to train a 3D Student. We systematically evaluated the impact of human-centric preprocessing, spatial augmentation, and soft-label regularization on both architectures. RESULTS | We identified a critical divergence in training dynamics. The 2D Teacher required strong spatial augmentation and soft-labeling to overcome data scarcity, improving White Matter Lesion Dice scores by>11 points. However, propagating these techniques to the 3D Student degraded its performance. Furthermore, human-centric preprocessing (e.g., CLAHE) disrupted global statistical cues, dropping Gray Matter Lesion Dice scores by ~25 points. DISCUSSION | Our study highlights a perception divergence (human-centric contrast enhancement harms machine models) and a regularization conflict across dimensions. 3D architectures trained on dense pseudo-labels exhibit fundamentally different optimization landscapes than 2D counterparts and require distinct, conservative regularization. Code and models: https://github.com/ivadomed/model_seg_sc-gm-lesion_human_ms_exvivo_t2star.

2026-05-11

arXiv (prépublication)

doi.org

arxiv.org

Probabilistic Calibration Is a Trainable Capability in Language Models

Sruthi Kuriakose

Language models are increasingly used in settings where outputs must satisfy user-specified randomness constraints, yet their generation pro… (voir plus)babilities are often poorly calibrated to those targets. We study whether this capability can be improved directly through fine-tuning. Concretely, we fine-tune language models on synthetic prompts that require sampling from mathematical distributions, and compare two Calibration Fine-Tuning variants: a soft-target method that converts the desired output distribution into trie-derived next-token targets, and a hard-target method that trains on sampled completions from the same target distribution. Across 12 models spanning four families, both methods substantially improve structured-sampling fidelity on held-out distribution families and unseen parameter settings, showing that probabilistic calibration is a trainable capability. Under our selected training configurations, the two methods exhibit different empirical profiles: hard-target fine-tuning is often strongest on structured numeric sampling, while soft-target fine-tuning performs better on broader stochastic generation benchmarks, including open-ended random generation, multiple-choice answer-position balancing, and NoveltyBench. The gains sometimes reduce downstream capability, especially arithmetic reasoning, with costs varying by model. Overall, our results show that probabilistic calibration can be improved through fine-tuning, with our hard-target configuration favoring exact numeric fidelity and our soft-target configuration favoring broader stochastic transfer. Code is available at https://github.com/chandar-lab/calibration-finetuning.

2026-05-11

arXiv (prépublication)

doi.org

arxiv.org

scShapeBench: Discovering geometry from high dimensional scRNAseq data

Andrew J. Steindl

João Felipe Rocha

Brian Tshilengi Di Bassinga

Zachary Warren

Matthew Scicluna

César Miguel Valdez Cordova

Shabarni Gupta

Leire Torices

Daniel Neumann

Timothy J. Mann

Ihuan Gunawan

Dhananjay Bhaskar

John G. Lock

Christine L. Chaffer

Guy Wolf

Smita Krishnaswamy

High-dimensional point cloud data arise across many scientific domains, especially single-cell biology. The shapes or topologies of these da… (voir plus)tasets determine the types of information that can be extracted. For example, clustered data supports cell-type identification, trajectory structures support transition analysis, and archetypal structures capture continua of cellular behaviors. Existing analysis pipelines often assume a specific shape. The standard Seurat pipeline combines UMAP visualization with Louvain clustering and therefore assumes clustered data, while tools such as Monocle and SPADE assume tree-like structures, and flow-based models such as MIOFlow and Conditional Flow Matching target trajectories. Choosing which pipeline to apply is therefore often left to bioinformaticians who visually inspect datasets before selecting an analysis strategy. With the rise of agentic AI scientists, automating shape detection is increasingly important for selecting downstream analysis pipelines. To address this problem, we introduce scShapeBench, a benchmark dataset for shape detection containing both synthetic and expert-annotated single-cell datasets. Synthetic datasets are sampled from ground-truth skeleton graphs with controlled variance. Real single-cell datasets are curated from diverse sources and annotated by experts into four categories: clusters, single trajectory, multi-branching, and archetypal. We additionally introduce scReebTower, a baseline method that uses diffusion geometry to extract Reeb graphs and connect visualization with pipeline selection. We provide topology-aware evaluation metrics and compare scReebTower against PAGA and Mapper on synthetic and real data. Our results indicate that scReebTower outperforms existing baselines. Overall, our contributions span benchmarks, evaluation metrics, and a baseline for automated shape detection in single-cell data.

2026-05-11

arXiv (prépublication)

doi.org

arxiv.org

Sleep Spindle-Locked Targeted Memory Reactivation Enhances Declarative Memory Consolidation

Vaishali Mutreja

Prakriti Gupta

Ovidiu Lungu

Latifa Lazzouni

Ella Gabitov

Habib Benali

Hugo Jourde

Giovanni Beltrame

Emily BJ Coffey

Jean-Marc Lina

Geneviève Albouy

Bradley King

Arnaud Boutin

Julie Carrier

Julien Doyon

Abstract Study Objectives Sleep spindles are implicated in memory consolidation. Yet direct evidence linking spindle dynamics to declarative… (voir plus) memory outcomes remains limited. We thus tested whether targeted memory reactivation (TMR) time-locked to sleep spindles enhances declarative memory, and whether the temporal organization of stimulated spindles–trains versus isolated events–is selectively associated with distinct memory outcomes. Methods Twenty-eight healthy young adults learned image locations from two categories (animals, clothing) in a grid, each paired with a distinct auditory cue. During overnight NREM sleep, one cue was replayed time-locked to spindles detected in real-time using a closed-loop system (TMR condition); the other served as the non-reactivated control (No-TMR condition). Category-cue assignment was counterbalanced. Post-sleep recall, recognition accuracy, and movement time were assessed. Results Recall accuracy was significantly higher in the TMR than the No-TMR condition (93.96% vs. 90.61%, p = .024), whereas recognition accuracy ( p = .139) and movement time ( p = .651) did not differ. Stimulation intensity within spindle trains correlated with the TMR effect on recall (Spearman ρ = .531, p = .004), whereas the proportion of isolated spindle stimulations correlated with the TMR effect on recognition (ρ = .563, p = .002). Cross-associations were not significant. Conclusions Spindle-locked TMR enhances recall-based declarative memory retention. The selective association between spindle temporal clustering and memory outcomes suggests that train-embedded and isolated spindles support different aspects of memory consolidation, highlighting spindle temporal context as a functionally relevant dimension of sleep-dependent memory processing.

2026-05-11

bioRxiv (prépublication)

doi.org

A systematic review of human-LLM interactions in computational thinking empirical studies

Yimei Zhang

You Song

Doina Precup

Reihaneh Rabbany

Maria Cutumisu

2026-05-11

Computer Science Education (publié)

doi.org